Reward learning algorithms utilize human feedback to infer a reward function, which is then used to train an AI system. This human feedback is often a preference comparison, in which the human teacher compares several samples of AI behavior and chooses which they believe best accomplishes the objective. While reward learning typically assumes that all feedback comes from a single teacher, in practice these systems often query multiple teachers to gather sufficient training data. In this paper, we investigate this disparity, and find that algorithmic evaluation of these different sources of feedback facilitates more accurate and efficient reward learning. We formally analyze the value of information (VOI) when reward learning from teachers with varying levels of rationality, and define and evaluate an algorithm that utilizes this VOI to actively select teachers to query for feedback. Surprisingly, we find that it is often more informative to query comparatively irrational teachers. By formalizing this problem and deriving an analytical solution, we hope to facilitate improvement in reward learning approaches to aligning AI behavior with human values.

In this paper, we propose a new mutual information framework for multi-agent reinforcement learning to enable multiple agents to learn coordinated behaviors by regularizing the accumulated return with the simultaneous mutual information between multi-agent actions. By introducing a latent variable to induce nonzero mutual information between multi-agent actions and applying a variational bound, we derive a tractable lower bound on the considered MMI-regularized objective function. The derived tractable objective can be interpreted as maximum entropy reinforcement learning combined with uncertainty reduction of other agents actions. Applying policy iteration to maximize the derived lower bound, we propose a practical algorithm named variational maximum mutual information multi-agent actor-critic, which follows centralized learning with decentralized execution. We evaluated VM3-AC for several games requiring coordination, and numerical results show that VM3-AC outperforms other MARL algorithms in multi-agent tasks requiring high-quality coordination.

Offline reinforcement learning (RL) aims at learning an optimal strategy using a pre-collected dataset without further interactions with the environment. While various algorithms have been proposed for offline RL in the previous literature, the minimax optimality has only been (nearly) established for tabular Markov decision processes (MDPs). In this paper, we focus on offline RL with linear function approximation and propose a new pessimism-based algorithm for offline linear MDP. At the core of our algorithm is the uncertainty decomposition via a reference function, which is new in the literature of offline RL under linear function approximation. Theoretical analysis demonstrates that our algorithm can match the performance lower bound up to logarithmic factors. We also extend our techniques to the two-player zero-sum Markov games (MGs), and establish a new performance lower bound for MGs, which tightens the existing result, and verifies the nearly minimax optimality of the proposed algorithm. To the best of our knowledge, these are the first computationally efficient and nearly minimax optimal algorithms for offline single-agent MDPs and MGs with linear function approximation.

A zero-shot RL agent is an agent that can solve any RL task in a given environment, instantly with no additional planning or learning, after an initial reward-free learning phase. This marks a shift from the reward-centric RL paradigm towards "controllable" agents that can follow arbitrary instructions in an environment. Current RL agents can solve families of related tasks at best, or require planning anew for each task. Strategies for approximate zero-shot RL ave been suggested using successor features (SFs) [BBQ+ 18] or forward-backward (FB) representations [TO21], but testing has been limited. After clarifying the relationships between these schemes, we introduce improved losses and new SF models, and test the viability of zero-shot RL schemes systematically on tasks from the Unsupervised RL benchmark [LYL+21]. To disentangle universal representation learning from exploration, we work in an offline setting and repeat the tests on several existing replay buffers. SFs appear to suffer from the choice of the elementary state features. SFs with Laplacian eigenfunctions do well, while SFs based on auto-encoders, inverse curiosity, transition models, low-rank transition matrix, contrastive learning, or diversity (APS), perform unconsistently. In contrast, FB representations jointly learn the elementary and successor features from a single, principled criterion. They perform best and consistently across the board, reaching 85% of supervised RL performance with a good replay buffer, in a zero-shot manner.

In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance. However, even when the prior is useful for generalization, distilling it to RL agent often interferes with RL training and degenerates sample efficiency. Meanwhile, the agent is forgetful of the prior due to the non-stationary nature of RL. These observations suggest two extreme schedules of distillation: (i) over the entire training; or (ii) only at the end. Hence, we devise a stand-alone network distillation method to inject the consistency prior at any time (even after RL), and a simple yet efficient framework to automatically schedule the distillation. Specifically, the proposed framework first focuses on mastering train environments regardless of generalization by adaptively deciding which {\it or no} augmentation to be used for the training. After this, we add the distillation to extract the remaining benefits for generalization from all the augmentations, which requires no additional new samples. In our experiments, we demonstrate the utility of the proposed framework, in particular, that considers postponing the augmentation to the end of RL training.

Safe reinforcement learning (RL) trains a policy to maximize the task reward while satisfying safety constraints. While prior works focus on the performance optimality, we find that the optimal solutions of many safe RL problems are not robust and safe against carefully designed observational perturbations. We formally analyze the unique properties of designing effective observational adversarial attackers in the safe RL setting. We show that baseline adversarial attack techniques for standard RL tasks are not always effective for safe RL and propose two new approaches - one maximizes the cost and the other maximizes the reward. One interesting and counter-intuitive finding is that the maximum reward attack is strong, as it can both induce unsafe behaviors and make the attack stealthy by maintaining the reward. We further propose a robust training framework for safe RL and evaluate it via comprehensive experiments. This paper provides a pioneer work to investigate the safety and robustness of RL under observational attacks for future safe RL studies. Code is available at: \url{https://github.com/liuzuxin/safe-rl-robustness}

Ensemble sampling serves as a practical approximation to Thompson sampling when maintaining an exact posterior distribution over model parameters is computationally intractable. In this paper, we establish a regret bound that ensures desirable behavior when ensemble sampling is applied to the linear bandit problem. This represents the first rigorous regret analysis of ensemble sampling and is made possible by leveraging information-theoretic concepts and novel analytic techniques that may prove useful beyond the scope of this paper.

Graph matching (GM) has been a building block in various areas including computer vision and pattern recognition. Despite recent impressive progress, existing deep GM methods often have obvious difficulty in handling outliers, which are ubiquitous in practice. We propose a deep reinforcement learning based approach RGM, whose sequential node matching scheme naturally fits the strategy for selective inlier matching against outliers. A revocable action framework is devised to improve the agent's flexibility against the complex constrained GM. Moreover, we propose a quadratic approximation technique to regularize the affinity score, in the presence of outliers. As such, the agent can finish inlier matching timely when the affinity score stops growing, for which otherwise an additional parameter i.e. the number of inliers is needed to avoid matching outliers. In this paper, we focus on learning the back-end solver under the most general form of GM: the Lawler's QAP, whose input is the affinity matrix. Especially, our approach can also boost existing GM methods that use such input. Experiments on multiple real-world datasets demonstrate its performance regarding both accuracy and robustness.

Although parallelism has been extensively used in reinforcement learning (RL), the quantitative effects of parallel exploration are not well understood theoretically. We study the benefits of simple parallel exploration for reward-free RL in linear Markov decision processes (MDPs) and two-player zero-sum Markov games (MGs). In contrast to the existing literature, which focuses on approaches that encourage agents to explore a diverse set of policies, we show that using a single policy to guide exploration across all agents is sufficient to obtain an almost-linear speedup in all cases compared to their fully sequential counterpart. Furthermore, we demonstrate that this simple procedure is near-minimax optimal in the reward-free setting for linear MDPs. From a practical perspective, our paper shows that a single policy is sufficient and provably near-optimal for incorporating parallelism during the exploration phase.

Reinforcement learning (RL) involves performing exploratory actions in an unknown system. This can place a learning agent in dangerous and potentially catastrophic system states. Current approaches for tackling safe learning in RL simultaneously trade-off safe exploration and task fulfillment. In this paper, we introduce a new generation of RL solvers that learn to minimise safety violations while maximising the task reward to the extent that can be tolerated by the safe policy. Our approach introduces a novel two-player framework for safe RL called Distributive Exploration Safety Training Algorithm (DESTA). The core of DESTA is a game between two adaptive agents: Safety Agent that is delegated the task of minimising safety violations and Task Agent whose goal is to maximise the environment reward. Specifically, Safety Agent can selectively take control of the system at any given point to prevent safety violations while Task Agent is free to execute its policy at any other states. This framework enables Safety Agent to learn to take actions at certain states that minimise future safety violations, both during training and testing time, while Task Agent performs actions that maximise the task performance everywhere else. Theoretically, we prove that DESTA converges to stable points enabling safety violations of pretrained policies to be minimised. Empirically, we show DESTA's ability to augment the safety of existing policies and secondly, construct safe RL policies when the Task Agent and Safety Agent are trained concurrently. We demonstrate DESTA's superior performance against leading RL methods in Lunar Lander and Frozen Lake from OpenAI gym.